Please note this reading list is very outdated, I had hoped to find time to update it before sharing it separately, but I’ve become caught up in other projects, so I think it makes sense to share it now before it becomes even more outdated.
motivation
‘AI for societal uplift’ as a path to victory by Raymond Douglas — LW Post : Examines the conditions in which a “societal uplift”—epistemics + coordination + institutional steering—might or might not lead to positive outcomes
N Stories of Impact for Wise AI Advisors —Draft 🏗️ : Different stories about how wise AI advisors could be useful for having a positive impact on the world.
International AI projects should promote differential AI development by Will MacAskill —Substack : Argues that these projects should differentially favour capabilities related to “artificial wisdom”, such as forecasting, ethical deliberation and negotiation.
artificial wisdom
Imagining and building wise machines: The centrality of AI metacognition by Johnson, Karimi, Bengio, et al. — Paper , Summary : This paper argues that wisdom involves two kinds of strategies (task-level strategies & metacognitive strategies). Since current AI is pretty good at the former, they argue that we should pursue the latter as a path to increasing AI wisdom.
Finding the Wisdom to Build Safe AI by Gordon Seidoh Worley — LW post : Seidoh talks about his own journey toward becoming wiser through Zen and outlines a plan for building wise AI. In particular, he argues that it will be hard to produce wise AI without having a wise person to evaluate it.
Design Sketches: Angels-on-the-Shoulder by Owen-Cotton Barratt et al. — Article : Sketches some products that might help people make more decisions that they’d endorse.
Designing Artificial Wisdom: The Wise Workflow Research Organisation by Jordan Arel — EA forum post (🏆 won a runner-up prize in the AI Impacts competition): Jordan proposes mapping the workflows within an organisation that is researching a topic like AI safety or existential risk. AI could be used to automate or augment parts of their work. This proportion would increase over time. The hope is that this would eventually allow us to fully bootstrap an artificially wise system.
Should we just be building more datasets? by Gabriel Recchia — Substack (🏆 won 4th prize in the AI Impacts Competition): Argues that an underrated way of increasing the wisdom of AI systems would be building more datasets (whilst also acknowledging the risks).
Tentatively Against Making AIs ‘wise’ by Oscar Delany — EA forum post (🏆 won a runner-up prize in the AI impacts competition): This article argues that insofar as wisdom is conceived of as being more intuitive than carefully reasoned, pursuing AI wisdom would be a mistake as we need AI reasoning to be transparent. I’ve included this because it seems valuable to have at least one critical article.
Wisdom & AI - Community : “a network of Buddhist teachers, AI professionals and leadership experts”
neighbouring areas of research
What’s Important In “AI for Epistemics”?by Lukas Finnveden — Forethought : AI for Epistemics is a subtly different but overlapping area. It is close enough that this article is worth reading. It provides an overview of why you might want to work on this, heuristics for good interventions and concrete projects.
Using AI to enhance societal decision making — 80,000 Hours Career Profile : Discusses the reasons why someone might want to work on this, possible counter-arguments and ways of getting involved.
AI for AI Safety by Joe Carlsmith —LW post : Provides a strategic analysis of why AI for AI safety is important whether it’s for making direct safety progress, evaluating risks, restraining capabilities or improving “backdrop capacity”. Great diagrams.
AI Tools for Existential Securityby Lizka Vaintrob and Owen Cotton-Barratt — Forethought : Discusses how applications of AI can be used to reduce existential risks and suggests strategic implications.
Not Superintelligence: Supercoordination — Forum post[55]: This article suggests that software-mediated supercoordination could be beneficial for steering the world in positive directions, but also identifies the possibility of this ending up as a “horrorshow”.
human wisdom
Stanford Encyclopedia of Philosophy Article on Wisdom by Sharon Ryan - SEP article : SEP articles tend to be excellent, but also long and complicated. In contrast, this article maintains that level of quality whilst remaining short and accessible.
Thirty Years of Psychological Wisdom Research: What We Know About the Correlates of an Ancient Concept by Dong, Weststrate and Fournier - Paper : Providesan excellent overview of how different groups within psychology view wisdom.
The Quest for Artificial Wisdom by Sevilla - Paper : This article outlines how wisdom is viewed within the discipline of Contemplative Sciences. It has some discussion of how to apply this to AI, but much of this discussion seems outdated in light of the deep learning paradigm.
applications to governance
Wise AI support for government decision-making by Ashwin - Substack (🏆 Prize-winning entry in the AI Impacts Automation of Wisdom and Philosophy Competition ): This article convinced me that it isn’t too early to start trying to engage with government on wise AI. In particular, Ashwin considers the example of automating the Delphi process. He argues that even though you might begin by automating parts of the process, over time you could expand beyond this, for example, by helping the organisers figure out what questions they should be asking.
some of my own work
Potentially Useful Projects in Wise AI — EA forum post : An attempt to list projects which I would expect to be positive EV.
• Some Preliminary Notes on the Promise of a Wisdom Explosion : Defines a wisdom explosion as a recursive self-improvement feedback loop that enhances wisdom, unlike intelligence as per the more traditional intelligence explosion. Argues that wisdom tech is safer from a differential technology perspective.
• An Overview of "Obvious" Approaches to Training Wise AI Advisors : Compares four different high-level approaches to training wise AI: direct training, imitation learning, attempting to understand what wisdom is at a deep principled level and the scattergun approach. One of the competition judges wrote: “I can imagine this being a handy resource to look at when thinking about how to train wisdom, both as a starting point, a refresher, and to double-check that one hasn’t forgotten anything important”.
other
Phaedrus by Plato — Socratic dialogue 📜: This dialogue helped me realise that there are significant limitations to prepared speeches/writing compared to dialogue (the “living and ensouled word of the man who knows”). I think that this has implications when thinking about training wise AI advisors as well.
Reading List on Wise AI
Please note this reading list is very outdated, I had hoped to find time to update it before sharing it separately, but I’ve become caught up in other projects, so I think it makes sense to share it now before it becomes even more outdated.
motivation
‘AI for societal uplift’ as a path to victory by Raymond Douglas —
LW Post: Examines the conditions in which a “societal uplift”—epistemics + coordination + institutional steering—might or might not lead to positive outcomesN Stories of Impact for Wise AI Advisors —
Draft 🏗️: Different stories about how wise AI advisors could be useful for having a positive impact on the world.International AI projects should promote differential AI development by Will MacAskill —
Substack: Argues that these projects should differentially favour capabilities related to “artificial wisdom”, such as forecasting, ethical deliberation and negotiation.artificial wisdom
Imagining and building wise machines: The centrality of AI metacognition by Johnson, Karimi, Bengio, et al. —
Paper,Summary: This paper argues that wisdom involves two kinds of strategies (task-level strategies & metacognitive strategies). Since current AI is pretty good at the former, they argue that we should pursue the latter as a path to increasing AI wisdom.Finding the Wisdom to Build Safe AI by Gordon Seidoh Worley —
LW post: Seidoh talks about his own journey toward becoming wiser through Zen and outlines a plan for building wise AI. In particular, he argues that it will be hard to produce wise AI without having a wise person to evaluate it.Design Sketches: Angels-on-the-Shoulder by Owen-Cotton Barratt et al. —
Article: Sketches some products that might help people make more decisions that they’d endorse.Designing Artificial Wisdom: The Wise Workflow Research Organisation by Jordan Arel —
EA forum post(🏆 won a runner-up prize in the AI Impacts competition): Jordan proposes mapping the workflows within an organisation that is researching a topic like AI safety or existential risk. AI could be used to automate or augment parts of their work. This proportion would increase over time. The hope is that this would eventually allow us to fully bootstrap an artificially wise system.Should we just be building more datasets? by Gabriel Recchia —
Substack(🏆 won 4th prize in the AI Impacts Competition): Argues that an underrated way of increasing the wisdom of AI systems would be building more datasets (whilst also acknowledging the risks).Tentatively Against Making AIs ‘wise’ by Oscar Delany —
EA forum post(🏆 won a runner-up prize in the AI impacts competition): This article argues that insofar as wisdom is conceived of as being more intuitive than carefully reasoned, pursuing AI wisdom would be a mistake as we need AI reasoning to be transparent. I’ve included this because it seems valuable to have at least one critical article.Wisdom & AI -
Community: “a network of Buddhist teachers, AI professionals and leadership experts”neighbouring areas of research
What’s Important In “AI for Epistemics”? by Lukas Finnveden —
Forethought: AI for Epistemics is a subtly different but overlapping area. It is close enough that this article is worth reading. It provides an overview of why you might want to work on this, heuristics for good interventions and concrete projects.Using AI to enhance societal decision making —
80,000 Hours Career Profile: Discusses the reasons why someone might want to work on this, possible counter-arguments and ways of getting involved.AI for AI Safety by Joe Carlsmith —
LW post: Provides a strategic analysis of why AI for AI safety is important whether it’s for making direct safety progress, evaluating risks, restraining capabilities or improving “backdrop capacity”. Great diagrams.AI Tools for Existential Security by Lizka Vaintrob and Owen Cotton-Barratt —
Forethought: Discusses how applications of AI can be used to reduce existential risks and suggests strategic implications.Not Superintelligence: Supercoordination —
Forum post[55]: This article suggests that software-mediated supercoordination could be beneficial for steering the world in positive directions, but also identifies the possibility of this ending up as a “horrorshow”.human wisdom
Stanford Encyclopedia of Philosophy Article on Wisdom by Sharon Ryan -
SEP article: SEP articles tend to be excellent, but also long and complicated. In contrast, this article maintains that level of quality whilst remaining short and accessible.Thirty Years of Psychological Wisdom Research: What We Know About the Correlates of an Ancient Concept by Dong, Weststrate and Fournier -
Paper: Provides an excellent overview of how different groups within psychology view wisdom.The Quest for Artificial Wisdom by Sevilla -
Paper: This article outlines how wisdom is viewed within the discipline of Contemplative Sciences. It has some discussion of how to apply this to AI, but much of this discussion seems outdated in light of the deep learning paradigm.applications to governance
Wise AI support for government decision-making by Ashwin -
Substack(🏆 Prize-winning entry in theAI Impacts Automation of Wisdom and Philosophy Competition): This article convinced me that it isn’t too early to start trying to engage with government on wise AI. In particular, Ashwin considers the example of automating the Delphi process. He argues that even though you might begin by automating parts of the process, over time you could expand beyond this, for example, by helping the organisers figure out what questions they should be asking.some of my own work
Potentially Useful Projects in Wise AI —
EA forum post: An attempt to list projects which I would expect to be positive EV.My entry in the
AI Impacts Automation of Wisdom and Philosophy Competition(split into two parts):•
Some Preliminary Notes on the Promise of a Wisdom Explosion: Defines a wisdom explosion as a recursive self-improvement feedback loop that enhances wisdom, unlike intelligence as per the more traditional intelligence explosion. Argues that wisdom tech is safer from a differential technology perspective.•
An Overview of "Obvious" Approaches to Training Wise AI Advisors: Compares four different high-level approaches to training wise AI: direct training, imitation learning, attempting to understand what wisdom is at a deep principled level and the scattergun approach. One of the competition judges wrote: “I can imagine this being a handy resource to look at when thinking about how to train wisdom, both as a starting point, a refresher, and to double-check that one hasn’t forgotten anything important”.other
Phaedrus by Plato —
Socratic dialogue 📜: This dialogue helped me realise that there are significant limitations to prepared speeches/writing compared to dialogue (the “living and ensouled word of the man who knows”). I think that this has implications when thinking about training wise AI advisors as well.(This reading list was originally shared as part of Beyond Human Wisdom: Can Man Survive the Rise of AGI?, but I wanted to also share it as a separately linkable resource)